Ivan Baldo

ibaldonl

·

https://www.netlabs.us/

AI & ML interests

MLOps, Scalability, Performance, OnPremises

Recent Activity

upvoted an article 3 days ago

New in llama.cpp: Decision Models

liked a dataset 3 days ago

agents-last-exam/agents-last-exam

new activity 3 days ago

IFM/K2-Horizon-MoVA-36B-A4B:Independent testing shows the true capabilities of this model

View all activity

Organizations

None yet

upvoted an article 3 days ago

Article

New in llama.cpp: Decision Models

ggml-org

•

3 days ago

• 81

upvoted a collection about 2 months ago

Qwen3.6 WNA16

vLLM compatible. Tested with v0.26. • 5 items • Updated Aug 10 • 4

upvoted a collection 4 months ago

GSQ

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling, https://huggingface.co/papers/2604.18556 • 10 items • Updated Aug 22 • 15

upvoted 3 collections 6 months ago

DFlash

Block Diffusion for Flash Speculative Decoding • 23 items • Updated 23 days ago • 156

Qwen3.6

4 items • Updated Apr 22 • 501

Gemma 4

Our most intelligent open models to date • 16 items • Updated 6 days ago • 1.15k

upvoted a collection 7 months ago

ParoQuant

Pairwise Rotation Quantization • 26 items • Updated 23 days ago • 31

upvoted an article 7 months ago

Article

FINAL Bench: The Real Bottleneck to AGI Is Self-Correction

FINAL-Bench

•

Feb 21

• 20

upvoted a collection 8 months ago

Qwen3.5

21 items • Updated Mar 9 • 1.79k

upvoted an article 8 months ago

Article

🔢 INT4 vs FP4: The Future of 4-Bit Quantization

onekq

•

Nov 19, 2025

• 8

upvoted a collection about 1 year ago

Inference Optimized Checkpoints (with Model Optimizer)

A collection of generative models quantized and optimized for inference with Model Optimizer. • 98 items • Updated 18 days ago • 190

upvoted an article over 1 year ago

Article

Gemma 3n fully available in the open-source ecosystem!

+6

ariG23498, pcuenq, sergiopaniego, reach-vb, FL33TW00D-HF, Xenova, Steveeeeeeen, kashif

•

Jun 26, 2025

• 123

upvoted 4 collections over 1 year ago

Qwen3

84 items • Updated Dec 31, 2025 • 1.87k

Qwen3-Reranker

3 items • Updated Dec 31, 2025 • 73

Qwen3-Embedding

6 items • Updated Dec 31, 2025 • 172

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated Jul 21 • 218

upvoted a paper over 2 years ago

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 630